Samer Hanna

Samurdhi Karunaratne, Samer Hanna, Danijela Cabric

As the Internet of Things (IoT) continues to grow, ensuring the security of systems that rely on wireless IoT devices has become critically important. Deep learning-based passive physical layer transmitter authorization systems have been introduced recently for this purpose, as they accommodate the limited computational and power budget of such devices. These systems have been shown to offer excellent outlier detection accuracies when trained and tested on a fixed authorized transmitter set. However in a real-life deployment, a need may arise for transmitters to be added and removed as the authorized set of transmitters changes. In such cases, the system could experience long down-times, as retraining the underlying deep learning model is often a time-consuming process. In this paper, we draw inspiration from information retrieval to address this problem: by utilizing feature vectors as RF fingerprints, we first demonstrate that training could be simplified to indexing those feature vectors into a database using locality sensitive hashing (LSH). Then we show that approximate nearest neighbor search could be performed on the database to perform transmitter authorization that matches the accuracy of deep learning models, while allowing for more than 100x faster retraining. Furthermore, dimensionality reduction techniques are used on the feature vectors to show that the authorization latency of our technique could be reduced to approach that of traditional deep learning-based systems.

Samurdhi Karunaratne, Samer Hanna, Danijela Cabric

RF devices can be identified by unique imperfections embedded in the signals they transmit called RF fingerprints. The closed set classification of such devices, where the identification must be made among an authorized set of transmitters, has been well explored. However, the much more difficult problem of open set classification, where the classifier needs to reject unauthorized transmitters while recognizing authorized transmitters, has only been recently visited. So far, efforts at open set classification have largely relied on the utilization of signal samples captured from a known set of unauthorized transmitters to aid the classifier learn unauthorized transmitter fingerprints. Since acquiring new transmitters to use as known transmitters is highly expensive, we propose to use generative deep learning methods to emulate unauthorized signal samples for the augmentation of training datasets. We develop two different data augmentation techniques, one that exploits a limited number of known unauthorized transmitters and the other that does not require any unauthorized transmitters. Experiments conducted on a dataset captured from a WiFi testbed indicate that data augmentation allows for significant increases in open set classification accuracy, especially when the authorized set is small.

Samer Hanna, Chris Dick, Danijela Cabric

Blindly decoding a signal requires estimating its unknown transmit parameters, compensating for the wireless channel impairments, and identifying the modulation type. While deep learning can solve complex problems, digital signal processing (DSP) is interpretable and can be more computationally efficient. To combine both, we propose the dual path network (DPN). It consists of a signal path of DSP operations that recover the signal, and a feature path of neural networks that estimate the unknown transmit parameters. By interconnecting the paths over several recovery stages, later stages benefit from the recovered signals and reuse all the previously extracted features. The proposed design is demonstrated to provide 5% improvement in modulation classification compared to alternative designs lacking either feature sharing or access to recovered signals. The estimation results of DPN along with its blind decoding performance are shown to outperform a blind signal processing algorithm for BPSK and QPSK on a simulated dataset. An over-the-air software-defined-radio capture was used to verify DPN results at high SNRs. DPN design can process variable length inputs and is shown to outperform relying on fixed length inputs with prediction averaging on longer signals by up to 15% in modulation classification.